Policy Gradient Methods

Peters, J; Bagnell, JA

doi:10.1007/978-0-387-30164-8_640

Local TagsRelease HistoryDetailsSummary

Policy Gradient Methods

Peters, J., & Bagnell, J. (2010). Policy Gradient Methods. In C. Sammut, & G. Webb (Eds.), Encyclopedia of Machine Learning (pp. 774-776). Berlin, Germany: Springer.

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-BD40-C Version Permalink: https://hdl.handle.net/21.11116/0000-0002-951C-7

Genre: Book Chapter

Files

show Files

Locators

show

hide

Locator:
https://link.springer.com/content/pdf/10.1007%2F978-0-387-30164-8_640.pdf (Publisher version) Open Access status unknown

Description:
-

OA-Status:

Creators

show

hide

Creators:
Peters, J^{1, 2}, Author
Bagnell, JA, Author

Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794

Content

show

hide

Free keywords: -

Abstract: A policy gradient method is a reinforcement learning approach that directly optimizes a parametrized control policy by a variant of gradient descent. These methods belong to the class of policy search techniques that maximize the expected return of a policy in a fixed policy class, in contrast with traditional value function approximation approaches that derive policies from a value function. Policy gradient approaches have various advantages: they enable the straightforward incorporation of domain knowledge in policy parametrization and often an optimal policy is more compactly represented than the corresponding value function; many such methods guarantee to convergence to at least a locally optimal policy; the methods naturally handle continuous states and actions and often even imperfect state information. The counterveiling drawbacks include difficulties in off-policy settings, the potential for very slow convergence and high sample complexity, as well as identifying local optima that are not globally optimal.

Details

show

hide

Language(s):

Dates: Published in Print: 2010-12

Publication Status: Published in print

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: DOI: 10.1007/978-0-387-30164-8_640
BibTex Citekey: 6074

Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show

hide

Title: Encyclopedia of Machine Learning

Source Genre: Book

Creator(s):
Sammut, C, Editor
Webb, GI, Editor

Affiliations:
-

Publ. Info: Berlin, Germany : Springer

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 774 - 776 Identifier: ISBN: 978-0-387-30164-8